EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[Doc] Update FAQ and add test guidance (#1360)

Browse Source 
### What this PR does / why we need it?
- Add test guidance
- Add reduce layer guidance
- update faq on determinitic calculation

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
Mengqing Cao
2025-06-25 09:59:23 +08:00
committed by GitHub
parent 5f5800ba42
commit c1c5d56255
4 changed files with 225 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
docs/source/developer_guide/contributing.md
View File

@@ -4,7 +4,7 @@
It's recommended to set up a local development environment to build and test
before you submit a PR.
### Prepare environment and build
### Setup development environment
Theoretically, the vllm-ascend build is only supported on Linux because
`vllm-ascend` dependency `torch_npu` only supports Linux.
@@ -48,72 +48,11 @@ bash format.sh
git commit -sm "your commit info"
```
### Testing
🎉 Congratulations! You have completed the development environment setup.
Although vllm-ascend CI provide integration test on [Ascend](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_test.yaml), you can run it
locally. The simplest way to run these integration tests locally is through a container:
```bash
# Under Ascend NPU environment
git clone https://github.com/vllm-project/vllm-ascend.git
cd vllm-ascend
export IMAGE=vllm-ascend-dev-image
export CONTAINER_NAME=vllm-ascend-dev
export DEVICE=/dev/davinci1
# The first build will take about 10 mins (10MB/s) to download the base image and packages
docker build -t $IMAGE -f ./Dockerfile .
# You can also specify the mirror repo via setting VLLM_REPO to speedup
# docker build -t $IMAGE -f ./Dockerfile . --build-arg VLLM_REPO=https://gitee.com/mirrors/vllm
docker run --rm --name $CONTAINER_NAME --network host --device $DEVICE \
--device /dev/davinci_manager --device /dev/devmm_svm \
--device /dev/hisi_hdc -v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-ti $IMAGE bash
cd vllm-ascend
pip install -r requirements-dev.txt
pytest tests/
```
### Run doctest
vllm-ascend provides a `vllm-ascend/tests/e2e/run_doctests.sh` command to run all doctests in the doc files.
The doctest is a good way to make sure the docs are up to date and the examples are executable, you can run it locally as follows:
```{code-block} bash
:substitutions:
# Update DEVICE according to your device (/dev/davinci[0-7])
export DEVICE=/dev/davinci0
# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|
docker run --rm \
--name vllm-ascend \
--device $DEVICE \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it $IMAGE bash
# Run doctest
/vllm-workspace/vllm-ascend/tests/e2e/run_doctests.sh
```
This will reproduce the same environment as the CI: [vllm_ascend_doctest.yaml](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_doctest.yaml).
### Test locally
You can refer to [Testing](./testing.md) doc to help you setup testing environment and running tests locally.
## DCO and Signed-off-by

183
docs/source/developer_guide/testing.md Normal file
View File

@@ -0,0 +1,183 @@
# Testing
This secition explains how to write e2e tests and unit tests to verify the implementation of your feature.
## Setup test environment
The fastest way to setup test environment is to use the main branch container image:
:::::{tab-set}
:sync-group: e2e
::::{tab-item} Single card
:selected:
:sync: single
```{code-block} bash
:substitutions:
# Update DEVICE according to your device (/dev/davinci[0-7])
export DEVICE=/dev/davinci0
# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:main
docker run --rm \
--name vllm-ascend \
--device $DEVICE \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it $IMAGE bash
```
::::
::::{tab-item} Multi cards
:sync: multi
```{code-block} bash
:substitutions:
# Update the vllm-ascend image
export IMAGE=quay.io/ascend/vllm-ascend:main
docker run --rm \
--name vllm-ascend \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it $IMAGE bash
```
::::
:::::
After starting the container, you should install the required packages:
```bash
# Prepare
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
# Install required packages
pip install -r requirements-dev.txt
```
## Running tests
### Unit test
There are several principles to follow when writing unit tests:
- The test file path should be consistent with source file and start with `test_` prefix, such as: `vllm_ascend/worker/worker_v1.py` --> `tests/ut/worker/test_worker_v1.py`
- The vLLM Ascend test are using unittest framework, see [here](https://docs.python.org/3/library/unittest.html#module-unittest) to understand how to write unit tests.
- All unit tests can be run on CPU, so you must mock the device-related function to host.
- Example: [tests/ut/test_ascend_config.py](https://github.com/vllm-project/vllm-ascend/blob/main/tests/ut/test_ascend_config.py).
- You can run the unit tests using `pytest`:
```bash
cd /vllm-workspace/vllm-ascend/
# Run all single card the tests
pytest -sv tests/ut
# Run
pytest -sv tests/ut/test_ascend_config.py
```
### E2E test
Although vllm-ascend CI provide [e2e test](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_test.yaml) on Ascend CI, you can run it
locally.
:::::{tab-set}
:sync-group: e2e
::::{tab-item} Single card
:selected:
:sync: single
```bash
cd /vllm-workspace/vllm-ascend/
# Run all single card the tests
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/
# Run a certain test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/test_offline_inference.py
# Run a certain case in test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/test_offline_inference.py::test_models
```
::::
::::{tab-item} Multi cards test
:sync: multi
```bash
cd /vllm-workspace/vllm-ascend/
# Run all single card the tests
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/
# Run a certain test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/test_dynamic_npugraph_batchsize.py
# Run a certain case in test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/test_offline_inference.py::test_models
```
::::
:::::
This will reproduce e2e test: [vllm_ascend_test.yaml](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_test.yaml).
#### E2E test example:
- Offline test example: [`tests/e2e/singlecard/test_offline_inference.py`](https://github.com/vllm-project/vllm-ascend/blob/main/tests/e2e/singlecard/test_offline_inference.py)
- Online test examples: [`tests/e2e/singlecard/test_prompt_embedding.py`](https://github.com/vllm-project/vllm-ascend/blob/main/tests/e2e/singlecard/test_prompt_embedding.py)
- Correctness test example: [`tests/e2e/singlecard/test_aclgraph.py`](https://github.com/vllm-project/vllm-ascend/blob/main/tests/e2e/singlecard/test_aclgraph.py)
- Reduced Layer model test example: [test_torchair_graph_mode.py - DeepSeek-V3-Pruning](https://github.com/vllm-project/vllm-ascend/blob/20767a043cccb3764214930d4695e53941de87ec/tests/e2e/multicard/test_torchair_graph_mode.py#L48)
The CI resource is limited, you might need to reduce layer number of the model, below is an example of how to generate a reduced layer model:
1. Fork the original model repo in modelscope, we need all the files in the repo except for weights.
2. Set `num_hidden_layers` to the expected number of layers, e.g., `{"num_hidden_layers": 2,}`
3. Copy the following python script as `generate_random_weight.py`. Set the relevant parameters `MODEL_LOCAL_PATH`, `DIST_DTYPE` and `DIST_MODEL_PATH` as needed:
```python
import torch
from transformers import AutoTokenizer, AutoConfig
from modeling_deepseek import DeepseekV3ForCausalLM
from modelscope import snapshot_download
MODEL_LOCAL_PATH = "~/.cache/modelscope/models/vllm-ascend/DeepSeek-V3-Pruning"
DIST_DTYPE = torch.bfloat16
DIST_MODEL_PATH = "./random_deepseek_v3_with_2_hidden_layer"
config = AutoConfig.from_pretrained(MODEL_LOCAL_PATH, trust_remote_code=True)
model = DeepseekV3ForCausalLM(config)
model = model.to(DIST_DTYPE)
model.save_pretrained(DIST_MODEL_PATH)
```
### Run doctest
vllm-ascend provides a `vllm-ascend/tests/e2e/run_doctests.sh` command to run all doctests in the doc files.
The doctest is a good way to make sure the docs are up to date and the examples are executable, you can run it locally as follows:
```bash
# Run doctest
/vllm-workspace/vllm-ascend/tests/e2e/run_doctests.sh
```
This will reproduce the same environment as the CI: [vllm_ascend_doctest.yaml](https://github.com/vllm-project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_doctest.yaml).

37
docs/source/faqs.md
View File

@@ -126,3 +126,40 @@ And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the tenso
### 17. Failed to reinstall vllm-ascend from source after uninstalling vllm-ascend?
You may encounter the problem of C compilation failure when reinstalling vllm-ascend from source using pip. If the installation fails, it is recommended to use `python setup.py install` to install, or use `python setup.py clean` to clear the cache.
### 18. How to generate determinitic results when using vllm-ascend?
There are several factors that affect output certainty:
1. Sampler Method: using **Greedy sample** by setting `temperature=0` in `SamplingParams`, e.g.:
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0)
# Create an LLM.
llm = LLM(model="Qwen/Qwen2.5-0.5B-Instruct")
# Generate texts from the prompts.
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
2. Set the following enveriments parameters:
```bash
export LCCL_DETERMINISTIC = 1
export HCCL_DETERMINISTIC = 1
export ATB_MATMUL_SHUFFLE_K_ENABLE = 0
export ATB_LLM_LCOC_ENABLE = 0
```

1
docs/source/index.md
View File

@@ -57,6 +57,7 @@ user_guide/release_notes
:caption: Developer Guide
:maxdepth: 1
developer_guide/contributing
developer_guide/testing
developer_guide/versioning_policy
developer_guide/evaluation/index
:::